Dave Franzen

North Dakota State University | NDSU · School of Natural Resources

Improving corn (Zea mays L.) nitrogen (N) rate fertilizer recommendation tools can improve farmers’ profits and mitigate N pollution. Numerous approaches have been tested to improve these tools, but to date improvements for predicting economically optimum N rate (EONR) have been modest. This work's objective was to use ensemble learning to improve...

Based on a seminal paper published by Stanford in 1973, many land grant universities adopted N rate guidelines that used expected yield times a factor (such as 1.2 lb N/bu), with adjustments for previous crop, to formulate N rate recommendations for corn. However, discrepancies between yield‐based N rate recommendations and recent N response data l...

Accurate nitrogen (N) diagnosis early in the growing season across diverse soil, weather, and management conditions is challenging. Strategies using multi-source data are hypothesized to perform significantly better than approaches using crop sensing information alone. The objective of this study was to evaluate, across diverse environments, the po...

Development of predictive algorithms accounting for uncertainty in processes underpinning the maize (Zea Mays L.) yield response to nitrogen (N) are needed in order to provide new N fertilization guidelines. The aims of this study were to unravel the relative importance of crop management, soil, and weather factors on both the estimate and the size...

Maximum genetically possible crop growth and yield are inhibited by abiotic and or biotic stresses. Biotic stresses may include pests, insects or disease infestations whereas abiotic stress includes nutritional deficiencies. Sensors have been developed and are being developed to detect stresses and to assist in crop stress management. Decision supp...

Nitrogen fertilizer recommendations in corn (Zea mays L.) that match the economically optimal N fertilizer rate (EONR) are imperative for profitability and minimizing environmental degradation. However, the amount of soil N available for the crop depends on soil and weather factors, making it difficult to know the EONR from year‐to‐year and from fi...

The most common formsof S fertilizers in the northern Great Plains are ammonium sulfate (AS), ammonium thiosulfate (ATS), and elemental S (ES). Among these, AS is preferred over the others because of its readily available SO42– form, and it can be blended with other dry fertilizer granules, but SO42– is prone to leaching. Recently, fertilizer indus...

Improving corn (Zea mays L.) N management is pertinent to economic and environmental objectives. However, there are limited comprehensive data sources to develop and test N fertilizer decision aid tools across a wide geographic range of soil and weather scenarios. Therefore, a public‐industry partnership was formed to conduct standardized corn N ra...

Reports of sulfur (S) deficiency symptoms in corn (Zea mays L.) fields of the Red River Valley of North Dakota and Minnesota are increasing. Current soil tests cannot predict the availability of S correctly due to the presence of gypsum in soils of this region. Field trials were conducted to determine corn yield and S uptake response to incremental...

Improving corn (Zea mays L.) N fertilizer rate recommendation tools is necessary for improving farmers’ profits and minimizing N pollution. Research has repeatedly shown that weather and soil factors influence available N and crop N need. Adjusting available corn N recommendation tools with soil and weather measurements could improve farmers’ abili...

Maize (Zea Mays L.) yield responsiveness to nitrogen (N) fertilization depends on the yield under non-limiting N supply as well as on the inherent productivity under zero N fertilizer (Y0). Understanding the driving factors and developing predictive algorithms for Y0 will enhance the optimization of N fertilization in maize. Using a random forest a...

The exchangeable fraction of soil potassium (K) has been viewed as the most important source of plant-available K, with other sources playing smaller roles that do not influence the predictive value of a soil test. Thus, as K mass balance changes, the soil test should change correspondingly to be associated with greater or reduced plant availabilit...

Placement strategies can be a key determinant of efficient use of applied fertilizer potassium (K), given the relative immobility of K in all except the lightest textured soils or high rainfall environments. Limitations to K accessibility by plants caused by immobility in the soil are further compounded by the general lack of K-stimulated root prol...

Supply of adequate phosphorus (P) is critical at the early growth stages of corn (Zea mays L.), particularly under a cold environment like Northern Great Plains. The mutualistic relationship between arbuscular mycorrhizal fungi (AMF) and corn roots is responsible for supplying P. However, colonies of AMF drastically decline when corn follows a non‐...

Anaerobic potentially mineralizable N (PMN) combined with the pre‐plant nitrate test (PPNT) or pre‐sidedress nitrate test (PSNT) may improve corn (Zea mays L.) N management. Forty‐nine corn N response studies were conducted across the US Midwest to evaluate the capacity of the PPNT and PSNT to predict grain yield, N uptake, and economic optimal N r...

Soil microbes drive biological functions that mediate chemical and physical processes necessary for plants to sustain growth. Laboratory soil respiration has been proposed as one universal soil health indicator representing these functions, potentially informing crop and soil management decisions. Research is needed to test the premise that soil re...

The anaerobic potentially mineralizable N (PMN) test combined with the preplant (PPNT) and presidedress (PSNT) nitrate tests may improve corn (Zea mays L.) N fertilization predictions. Forty‐nine corn N response experiments (mostly corn following soybean [Glycine max (L.) Merr.]) were conducted in the US Midwest from 2014–2016 to evaluate the abili...

Understanding the variables that affect the anaerobic potentially mineralizable N (PMNan) test should lead to a standard procedure of sample collection and incubation length, improving PMNan as a tool in corn (Zea mays L) N management. We evaluated the effect of soil sample timing [preplant and V5 corn development stage (V5)], N fertilization (0 an...

Determining which corn (Zea mays L.) N fertilizer rate recommendation tools best predict crop N need would be valuable for maximizing profits and minimizing environmental consequences. Simultaneous comparisons of multiple tools across various environmental conditions have been limited. The objectives of this research were to evaluate the performanc...

Splitting the N application into two or more timings may improve corn (Zea mays L.) grain yield and N recovery relative to a single-N application. A 49 site-year study across eight U.S. Midwestern states compared the effect of an at-planting (single-N application) and two split-N applications [45 (45+SD) or 90 kg N ha−1 (90+SD) at planting with the...

Estimates of mineralizable N with the anaerobic potentially mineralizable N (PMNan) test could improve predictions of corn (Zea mays L.) economic optimal N rate (EONR). A study across eight US midwestern states was conducted to quantify the predictability of EONR for single and split N applications by PMNan. Treatment factors included different soi...

In the Northern Great Plains, sugarbeet (Beta vulgaris L.) harvesting is stretched out from August to October. Sensors mounted on unmanned aerial vehicles (UAVs) may provide the information needed to identify sugarbeet approaching an optimum harvesting date that maximizes the recoverable sugar yield. The objective of this study was to relate the ve...

Nitrogen (N) fertilizer recommendation tools could be improved for estimating corn (Zea mays L.) N needs by incorporating site-specific soil and weather information. However, an evaluation of analytical methods is needed to determine the success of incorporating this information. The objectives of this research were to evaluate statistical and mach...

Nitrogen provided to crops through mineralization is an important factor in N management guidelines. Understanding of the interactive effects of soil and weather conditions on N mineralization needs to be improved. Relationships between anaerobic potentially mineralizable N (PMNan) and soil and weather conditions were evaluated under the contrastin...

Due to initially high soil test K values, K soil test correlation and calibration for corn in North Dakota has previously not been intensely investigated. Potassium fertilizer rate experiments were conducted on 25 sites from 2014 to 2016. The previously published soil test K critical value of 150 mg kg ⁻¹ predicted crop response correctly at 16 of...

Topographic features impact biomass and other agriculturally relevant observables. However, conventional tools for processing digital elevation model (DEM) data in geographic information systems have severe limitations. Typically, 3-by-3 window sizes are used for evaluating the slope, aspect and curvature. As a consequence, high resolution DEMs hav...

Active-optical (AO) sensors have been used in several crops as a yield-prediction tool for N management, but not in sunflower (Helianthus annuus). The need for in-season N and its rate can be determined through using a yield and AO relationship. By comparing predicted yield from an area of sufficient N to another area of the field, the yield differ...

A series of N-rate experiments was previously conducted in spring wheat, corn and sunflower in North Dakota indicated that less N was required when fields were in 6-years or more continuous no-till compared to conventional till. The objective of this study was to determine whether part of the reason for the decreased requirement for N was the great...

Active-optical reflectance sensors (AORS) use light reflectance characteristics from a crop canopy as an indicator of the plant’s N health. However, studies have shown AORS algorithms used in conjunction with measured reflectance characteristics for corn (Zea mays L.) N fertilizer rate recommendations are not consistently accurate. Our objective wa...

Determination of in-season N requirement for corn (Zea mays L.) is challenging due to interactions of genotype, environment, and management. Machine learning (ML), with its predictive power to tackle complex systems, may solve this barrier in the development of locally based N recommendations. The objective of this study was to explore application...

Uncertainty exists with corn (Zea mays L.) N management due to year-to-year variation in crop N need, soil N supply, and N loss from leaching, volatilization, and denitrification. Active-optical reflectance sensing (AORS) has proven effective in some fields for generating N fertilizer recommendations that improve N use efficiency, but locally deriv...

Slope computations in Geographic Information Systems are typically done over windows of sizes as small as 3×3 pixels, and the algorithms that are used do not scale to very large windows. Considering the abundance of high-resolution Digital Elevation Model (DEM) data, these algorithms are inadequate for providing high-quality processed data efficien...

Use and development of soil biological tests for estimating soil nitrogen (N) availability and subsequently corn (Zea mays L.) fertilizer N recommendations is garnering considerable interest.The objective of this research was to evaluate relationships between the Haney Soil Health Test (HSHT), also known as the Soil Health Tool or Haney test, and t...

Fertilizer N application is critical to optimize sugarbeet (Beta vulgaris L.) yield and sugar concentration. Regardless of observed yields, current fertilizer recommendations in North Dakota and Minnesota suggest a single application rate of 146 kg N ha–1 (considering both fertilizer N residual soil N of 120 cm depth) for the Red River Valley (RRV)...

Ground-based active optical sensors (GBAOS) have been successfully used in agriculture to predict crop yield potential (YP) early in the season and to improvise N rates for optimal crop yield. However, the models were found weak or inconsistent due to environmental variation especially rainfall. The objectives of the study were to evaluate if GBAOS...

Ground-based active optical sensors (GBAOS) have been successfully used in agriculture to predict crop yield potential (YP) early in the season and to improvise N rates for optimal crop yield. However, the models were found weak or inconsistent due to environmental variation especially rainfall. The objectives of the study were to evaluate if GBAOS...

The N and P recommendations for sunflowers growers in North Dakota have not been changed in 30 yr. Twenty-two N and P rate experiments were conducted during 2014 and 2015. The objective was to determine the response of seed yield, oil concentration, and lodging to available N and P. In 2014 studies were a randomized complete block split plot with N...

This is a paper that compares the effect of single near planting nitrogen fertilizer applications and splitting up the nitrogen fertilizer application on soil nitrate-nitrogen content and corn grain yield

Reclamation of sodic soils is proving increasingly vital as greater land area becomes salt-affected in the northern Great Plains of the United States. Flue gas desulfurization gypsum (FGDG) can be an agriculturally important resource for increasing land productivity through the ameliorating of sodic soils. Biochar is also considered as an aid in re...

Due to economic and environmental consequences of N lost from fertilizer applications in corn (Zea mays L.), considerable public and industry attention has been devoted to the development of N decision tools. Needed are research and databases and associated metadata, at numerous locations and years to represent a wide geographic range of soil and w...

Concerns for environmental sustainability are leading to a growing interest understanding geospatial data. At the same time, the availability of high-resolution imagery from satellites and unmanned air systems is increasing rapidly. However, the processing techniques that are available within geographic information systems are not yet adapted to bi...

This paper evaluates the use of the anaerobic potentially mineralizable nitrogen test as an index for nitrogen mineralization and its use to estimate N fertilizer needs of corn.

The demand for improved decision-making products for cereal production systems has placed added emphasis on using plant sensors in-season, and that incorporate real-time, site specific, growing environments. The objectives of this work were to describe validated in-season sensor-based algorithms presently being used in cereal grain production syste...

Prediction of S deficiency is difficult due to poor soil test relationship to crop response. The purpose of this article is to provide evidence that the use of an N-sufficient area established for use as a standard for active-optical (AO) sensor directed in-season N application could also serve to detect S deficiency in corn (Zea mays L.). Nitrogen...

Corn height measured manually has shown promising results in improving the relationship between active-optical (AO) sensor readings and crop yield. Manual measurement of corn height is not practical in US commercial corn production, so an alternative automatic method must be found in order to capture the benefit of including canopy height into in-s...

Potassium (K) fertilizer recommendations are mainly based on air -dried soil samples which can lead to over- or under-estimation of plant available soil K. Three on-farm trials were conducted in North Dakota and Minnesota to determine the variation of soil test-K between air-dried (KDry) and field moist (KMoist) soil samples. The differences betwee...

Algorithms using active-optical (AO) sensors have been developed to direct in-season N application to crops. Many farmers in the United States have a large number of farm fields to manage. Farmers using AO technology must visit each field and operate the sensor across the entire field in order to conduct in-season N application. A field might be dr...

Thirty field experiments were conducted in North Dakota during 2011 and 2012 to compare two ground-based active-optical sensors for their relationship between sensor readings and INSEY (in-season estimate of yield). The experimental design at each site was a randomized complete block with four replications and six nitrogen (N)rate treatments: contr...

Active-optical sensor readings from an N non-limiting area standard established within a farm field are used to predict yield in the standard. Lower yield predictions from sensor readings obtained from other parts of the field outside of the N non-limiting standard area indicate a need for supplemental N. Active-optical sensor algorithms for predic...

Nitrogen management for corn (Zea mays L.) may be improved by applying a portion of N in-season. This investigation was conducted to evaluate crop modeling (Maize-N) and active crop canopy sensing approaches for recommending in-season N fertilizer rates. These approaches were evaluated during 2012-2013 on 11 field sites, in Missouri, Nebraska, and...

Saturated paste derived sodium adsorption ratio (SARe) is not a routine procedure for soil testing laboratories in the northern Great Plains. The objective of this study was to determine the relationship between SARe, a solution-phase only extraction, and percentage of Na (%Na; Na/(Na+Ca+Mg+K), a solution phase plus exchange phase value using 1M am...

The soil potassium (K) test methodology is under increased evaluation due to the soil sample drying effect, temporal variations of test results and inconsistent crop response to applied K fertilizers. Ten on-farm trials were conducted in 2014 in eastern North Dakota to determine the corn response to different K-fertilizer rates and to assess the va...

Yield prediction in sugar beet (Beta vulgaris L.) is important as a basis for in-season N application. Active optical sensors have been researched in sugar beet for yield estimation. A common field method for using active-optical sensors is to establish an N non-limiting area, and compare the yield predicted from sensor readings withreadings from t...

Active optical light sensors have been available for agricultural use for about 20 years. People are most familiar with passive light sensors. A passive light sensor can detect visible light and other electro-magnetic radiation originally emitted by the sun or another light source. The instrument senses the reflection of the light. Examples of pass...

Early in-season loss of N continues to be a problem in corn (Zea mays L.). One method to improve N use efficiency is fertilizing based on in-season crop foliage sensors. The objective of this study was to evaluate two ground-based, active-optical (GBAO) sensors and explore the use of corn height with sensor readings for improving relationships with...

Corn has been a crop in North Dakota for at least 100 years. However, the acres under corn grain production have been relatively small, compared with small-grain crops, until about 20 years ago. Today, corn consistently is planted on more than 3 million acres each year, with most North Dakota counties having signifi cant acreage. The surge in acrea...

Yield prediction is important for making in-season agronomic input decisions and for greater logistical decisions. In predicting the crop yield based on ground-based active optical sensing data, the ordinary statistical unweighted linear or nonlinear regression models are the most popular choices. However, these unweighted models may not be accurat...

A series of nitrogen rate experiments were established in sugar beet (Beta vulgaris, L), sunflower (Helianthus annuus, L), and spring wheat (Triticum aestivum, L) in 2012. Two active-optical sensors were used in sugar beet and sunflower at the 6 leaf stage and again about two weeks after the first reading. The sensors were used at flag leaf (Zadoks...

Nitrogen Nodulation Although the atmosphere is 78 percent nitrogen gas, plants cannot use it directly. Plants can use only ammonium-N or nitrate-N. Soybean is a legume and normally should provide itself N through a symbiotic relationship with N-fi xing bacteria of the species Bradyrhizobium japonicum. In this symbiotic relationship, carbohydrates a...

Textural features extracted from LANDSAT satellite image and non-imagery information like soil electrical conductivity, crop yield, topography, and crop dry residue matter etc., were used to develop residual soil nitrate prediction models using three neural networks; back propagation, modular, and radial basis function architectures. Statistical pa...